Suppr超能文献

文本与音频简化:人类与ChatGPT对比

Text and Audio Simplification: Human vs. ChatGPT.

作者信息

Leroy Gondy, Kauchak David, Harber Philip, Pal Ankit, Shukla Akash

机构信息

University of Arizona, Tucson, AZ.

Pomona College, Claremont, CA.

出版信息

AMIA Jt Summits Transl Sci Proc. 2024 May 31;2024:295-304. eCollection 2024.

Abstract

Text and audio simplification to increase information comprehension are important in healthcare. With the introduction of ChatGPT, evaluation of its simplification performance is needed. We provide a systematic comparison of human and ChatGPT simplified texts using fourteen metrics indicative of text difficulty. We briefly introduce our online editor where these simplification tools, including ChatGPT, are available. We scored twelve corpora using our metrics: six text, one audio, and five ChatGPT simplified corpora (using five different prompts). We then compare these corpora with texts simplified and verified in a prior user study. Finally, a medical domain expert evaluated the user study texts and five, new ChatGPT simplified versions. We found that simple corpora show higher similarity with the human simplified texts. ChatGPT simplification moves metrics in the right direction. The medical domain expert's evaluation showed a preference for the ChatGPT style, but the text itself was rated lower for content retention.

摘要

在医疗保健领域,简化文本和音频以提高信息理解能力非常重要。随着ChatGPT的推出,需要对其简化性能进行评估。我们使用十四种表示文本难度的指标,对人工简化文本和ChatGPT简化文本进行了系统比较。我们简要介绍了我们的在线编辑器,在该编辑器中可以使用包括ChatGPT在内的这些简化工具。我们使用我们的指标对十二个语料库进行了评分:六个文本语料库、一个音频语料库和五个ChatGPT简化语料库(使用五个不同的提示)。然后,我们将这些语料库与之前用户研究中简化并验证过的文本进行比较。最后,一位医学领域专家对用户研究文本和五个新的ChatGPT简化版本进行了评估。我们发现,简单的语料库与人工简化文本具有更高的相似度。ChatGPT简化使各项指标朝着正确的方向发展。医学领域专家的评估显示,他们对ChatGPT的风格更青睐,但对文本内容保留率的评分较低。

相似文献

1
Text and Audio Simplification: Human vs. ChatGPT.文本与音频简化:人类与ChatGPT对比
AMIA Jt Summits Transl Sci Proc. 2024 May 31;2024:295-304. eCollection 2024.
7
Parallel Sentence Alignment from Biomedical Comparable Corpora.生物医学可比语料库中的平行句子对齐
Stud Health Technol Inform. 2020 Jun 16;270:362-366. doi: 10.3233/SHTI200183.

本文引用的文献

1
Evaluating Factuality in Text Simplification.评估文本简化中的事实性。
Proc Conf Assoc Comput Linguist Meet. 2022 May;2022:7331-7345. doi: 10.18653/v1/2022.acl-long.506.
3
A survey of automated methods for biomedical text simplification.生物医学文本简化的自动化方法调查。
J Am Med Inform Assoc. 2022 Oct 7;29(11):1976-1988. doi: 10.1093/jamia/ocac149.
5
Impact of the Text Simplification on Understanding.文本简化对理解的影响。
Stud Health Technol Inform. 2022 May 25;294:634-638. doi: 10.3233/SHTI220546.
7
Orthodontic treatment consent forms: A readability analysis.正畸治疗同意书:可读性分析。
J Orthod. 2022 Mar;49(1):32-38. doi: 10.1177/14653125211033301. Epub 2021 Jul 29.
9
Measuring Text Difficulty Using Parse-Tree Frequency.利用句法树频率测量文本难度
J Assoc Inf Sci Technol. 2017 Sep;68(9):2088-2100. doi: 10.1002/asi.23855. Epub 2017 Jun 20.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验